Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 6746
    Prev
    Next
    INDEX
    Explanations

    Code review requests

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Environmental
    -0.07
     entrepreneurs
    -0.07
     Dude
    -0.07
    .lastName
    -0.07
    社会效益
    -0.06
    .metrics
    -0.06
     איש
    -0.06
    Contact
    -0.06
     programas
    -0.06
    不合格
    -0.06
    POSITIVE LOGITS
    jur
    0.08
    Het
    0.07
    it
    0.07
    woke
    0.07
     orderby
    0.07
    身形
    0.07
    ],$
    0.07
     maintaining
    0.07
    世纪
    0.07
    Cannot
    0.07
    Activations Density 0.028%

    No Known Activations